{"id":"https://openalex.org/W4405786996","doi":"https://doi.org/10.1109/iros58592.2024.10802484","title":"Multimodal Evolutionary Encoder for Continuous Vision-Language Navigation","display_name":"Multimodal Evolutionary Encoder for Continuous Vision-Language Navigation","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786996","doi":"https://doi.org/10.1109/iros58592.2024.10802484"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089600727","display_name":"Zongtao He","orcid":"https://orcid.org/0000-0002-2166-4450"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongtao He","raw_affiliation_strings":["Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080359598","display_name":"Liuyi Wang","orcid":"https://orcid.org/0000-0003-1368-0300"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liuyi Wang","raw_affiliation_strings":["Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112119162","display_name":"Lu Chen","orcid":"https://orcid.org/0009-0003-3335-6521"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Chen","raw_affiliation_strings":["Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404309","display_name":"Shu Li","orcid":"https://orcid.org/0000-0001-8225-5426"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Li","raw_affiliation_strings":["Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100941392","display_name":"Qingqing Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingqing Yan","raw_affiliation_strings":["Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037285766","display_name":"Chengju Liu","orcid":"https://orcid.org/0000-0001-7543-0855"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengju Liu","raw_affiliation_strings":["Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073789459","display_name":"Qijun Chen","orcid":"https://orcid.org/0000-0001-5644-1188"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qijun Chen","raw_affiliation_strings":["Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1443","last_page":"1450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9645000100135803,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9645000100135803,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9603999853134155,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9577000141143799,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7186329364776611},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5930745005607605},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5125527381896973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4617822766304016},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3418096899986267},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.05929887294769287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186329364776611},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5930745005607605},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5125527381896973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4617822766304016},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3418096899986267},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.05929887294769287}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1861492603","https://openalex.org/W1985238052","https://openalex.org/W2021851106","https://openalex.org/W2108598243","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2594519801","https://openalex.org/W2780351918","https://openalex.org/W2886641317","https://openalex.org/W2890902815","https://openalex.org/W2926977875","https://openalex.org/W2963800628","https://openalex.org/W2964199361","https://openalex.org/W2964339842","https://openalex.org/W2979727876","https://openalex.org/W3034758614","https://openalex.org/W3094502228","https://openalex.org/W3105521436","https://openalex.org/W3109085430","https://openalex.org/W3109097593","https://openalex.org/W3172675210","https://openalex.org/W3175443984","https://openalex.org/W3176641147","https://openalex.org/W3176974620","https://openalex.org/W3195026654","https://openalex.org/W3203338521","https://openalex.org/W3206064780","https://openalex.org/W4205161929","https://openalex.org/W4226052928","https://openalex.org/W4312253995","https://openalex.org/W4312544224","https://openalex.org/W4312729859","https://openalex.org/W4312996039","https://openalex.org/W4313427326","https://openalex.org/W4385245566","https://openalex.org/W4386076252","https://openalex.org/W4401109681","https://openalex.org/W6639432524","https://openalex.org/W6640174482","https://openalex.org/W6751885507","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6766947841","https://openalex.org/W6769627184","https://openalex.org/W6773029903","https://openalex.org/W6791353385","https://openalex.org/W6800673378","https://openalex.org/W6803039797","https://openalex.org/W6846007759","https://openalex.org/W6850630192"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Can":[0],"multimodal":[1,37,44,54],"encoder":[2,39,45,55,90,104],"evolve":[3],"when":[4],"facing":[5],"increasingly":[6,92],"tough":[7],"circumstances?":[8],"Our":[9,171],"work":[10],"investigates":[11],"this":[12],"possibility":[13],"in":[14,156],"the":[15,65,79,89,103,132,143],"context":[16],"of":[17,68,134,145],"continuous":[18,136],"vision-language":[19],"navigation":[20],"(continuous":[21],"VLN),":[22],"which":[23],"aims":[24],"to":[25,63,91,115],"navigate":[26],"robots":[27],"under":[28],"linguistic":[29],"supervision":[30],"and":[31,47,61,70,96,108,111,166,173],"visual":[32],"feedback.":[33],"We":[34],"propose":[35],"a":[36,42,124],"evolutionary":[38,49,85],"(MEE)":[40],"comprising":[41],"unified":[43,53],"architecture":[46],"an":[48],"pre-training":[50,86],"strategy.":[51],"The":[52,84,99],"unifies":[56],"rich":[57],"modalities,":[58],"including":[59],"depth":[60],"sub-instruction,":[62],"enhance":[64],"solid":[66],"understanding":[67],"environments":[69],"tasks.":[71],"It":[72],"also":[73],"effectively":[74],"utilizes":[75],"monocular":[76],"observation,":[77],"reducing":[78],"reliance":[80],"on":[81,140],"panoramic":[82],"vision.":[83],"strategy":[87],"exposes":[88],"unfamiliar":[93,116],"data":[94],"domains":[95],"difficult":[97],"objectives.":[98],"multi-stage":[100,126],"adaption":[101],"helps":[102],"establish":[105],"robust":[106],"intra-":[107],"inter-modality":[109],"connections":[110],"improve":[112],"its":[113,164],"generalization":[114],"environments.":[117],"To":[118],"achieve":[119],"such":[120],"evolution,":[121],"we":[122,153],"collect":[123],"large-scale":[125],"dataset":[127,174],"with":[128],"specialized":[129],"objectives,":[130],"addressing":[131],"absence":[133],"suitable":[135],"VLN":[137],"pre-training.":[138],"Evaluation":[139],"VLN-CE":[141],"demonstrates":[142],"superiority":[144],"MEE":[146,155],"over":[147],"other":[148],"direct":[149],"action-predicting":[150],"methods.":[151],"Furthermore,":[152],"deploy":[154],"real":[157],"scenes":[158],"using":[159],"self-developed":[160],"service":[161],"robots,":[162],"showcasing":[163],"effectiveness":[165],"potential":[167],"for":[168],"real-world":[169],"applications.":[170],"code":[172],"are":[175],"available":[176],"at":[177],"https://github.com/RavenKiller/MEE.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}